Institution
Company•Tel Aviv, Israel•
About: Facebook is a company organization based out in Tel Aviv, Israel. It is known for research contribution in the topics: Computer science & Artificial neural network. The organization has 7856 authors who have published 10906 publications receiving 570123 citations. The organization is also known as: facebook.com & FB.
Topics: Computer science, Artificial neural network, Language model, Context (language use), Reinforcement learning
Papers published on a yearly basis
Papers
More filters
•
13 Sep 2012TL;DR: In this paper, a geo-social networking system determines a user's current location, calculates a novelty score for the location representing the user's degree of familiarity, and surfaces content within a geographic and temporal radius based on the novelty score.
Abstract: In one embodiment, a geo-social networking system determines a user's current location, calculates a novelty score for the location representing the user's degree of familiarity, and surfaces content within a geographic and temporal radius based on the novelty score for display to the user.
127 citations
•
23 Jun 2015TL;DR: In this paper, a method was proposed to find the first person in an image portraying at least a first person, accessing a social graph, determining a social-graph affinity for a first set of users and determining a facial-recognition scores for the first set.
Abstract: In one embodiment, a method includes accessing an image portraying at least a first person, accessing a social graph, determining a social-graph affinity for a first set of users, determining a facial-recognition scores for the first set of users based on the social-graph affinity for each user and a facial-representation associated with each user, where the facial-representation for each user is compared with the image, and generating one or more tag suggestions for the first person portrayed in the image based on the facial-recognition scores.
127 citations
•
12 Jan 2012TL;DR: In this article, a mobile device performs an over-the-air firmware update by writing the updated firmware to a inactive system image partition, and rebooting the device, and the security of the OTA update is maintained through checking a plurality of security signatures in an OTA manifest.
Abstract: In one embodiment, a mobile device performs an over-the-air firmware update by writing the updated firmware to a inactive system image partition, and rebooting the device. The security of the OTA update is maintained through checking a plurality of security signatures in an OTA manifest, and the integrity of the data is maintained by checking a hash value of the downloaded system image.
127 citations
•
TL;DR: In this paper, a dense-sparse-densemble training flow is proposed for regularizing deep neural networks and achieving better optimization performance. But it is difficult to train a large number of parameters, making them very hard to train.
Abstract: Modern deep neural networks have a large number of parameters, making them very hard to train. We propose DSD, a dense-sparse-dense training flow, for regularizing deep neural networks and achieving better optimization performance. In the first D (Dense) step, we train a dense network to learn connection weights and importance. In the S (Sparse) step, we regularize the network by pruning the unimportant connections with small weights and retraining the network given the sparsity constraint. In the final D (re-Dense) step, we increase the model capacity by removing the sparsity constraint, re-initialize the pruned parameters from zero and retrain the whole dense network. Experiments show that DSD training can improve the performance for a wide range of CNNs, RNNs and LSTMs on the tasks of image classification, caption generation and speech recognition. On ImageNet, DSD improved the Top1 accuracy of GoogLeNet by 1.1%, VGG-16 by 4.3%, ResNet-18 by 1.2% and ResNet-50 by 1.1%, respectively. On the WSJ'93 dataset, DSD improved DeepSpeech and DeepSpeech2 WER by 2.0% and 1.1%. On the Flickr-8K dataset, DSD improved the NeuralTalk BLEU score by over 1.7. DSD is easy to use in practice: at training time, DSD incurs only one extra hyper-parameter: the sparsity ratio in the S step. At testing time, DSD doesn't change the network architecture or incur any inference overhead. The consistent and significant performance gain of DSD experiments shows the inadequacy of the current training methods for finding the best local optimum, while DSD effectively achieves superior optimization performance for finding a better solution. DSD models are available to download at this https URL.
127 citations
•
07 Jan 2011TL;DR: In this paper, instant messaging (IM) entities may be invited to an electronic calendar event using an instant message using an IM buddy list, and selecting the IM entities as invitees to the event may include dragging and dropping names of IM entities from a buddy list of an IM application to an event from an e-calendar application, or vice versa.
Abstract: Instant messaging (IM) entities may be invited to an electronic calendar event using an instant message. Selecting the IM entities as invitees to the event may include dragging and dropping names of the IM entities from a buddy list of an IM application to an event from an electronic calendar application, or vice versa. A method of inviting an entity to a calendar event includes providing a calendar event from a calendar application and recognizing, by the calendar application, an IM entity as an invitee to the event.
127 citations
Authors
Showing all 7875 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yoshua Bengio | 202 | 1033 | 420313 |
Xiang Zhang | 154 | 1733 | 117576 |
Jitendra Malik | 151 | 493 | 165087 |
Trevor Darrell | 148 | 678 | 181113 |
Christopher D. Manning | 138 | 499 | 147595 |
Robert W. Heath | 128 | 1049 | 73171 |
Pieter Abbeel | 126 | 589 | 70911 |
Yann LeCun | 121 | 369 | 171211 |
Li Fei-Fei | 120 | 420 | 145574 |
Jon Kleinberg | 117 | 444 | 87865 |
Sergey Levine | 115 | 652 | 59769 |
Richard Szeliski | 113 | 359 | 72019 |
Sanjeev Kumar | 113 | 1325 | 54386 |
Bruce Neal | 108 | 561 | 87213 |
Larry S. Davis | 107 | 693 | 49714 |